Credit time series data modeling method and device based on convolutional neural network

The invention discloses a credit time series data modeling method and device based on a convolutional neural network, and the method comprises the steps: obtaining historical data which comprises business data and time series data, converting the business data and the time series data, and obtaining a customer data two-dimensional matrix; obtaining an initial neural network model, training the initial neural network model according to the customer data two-dimensional matrix, performing convolution, activation and pooling operation on the input two-dimensional matrix during each training, and updating model parameters after each training; and after a preset condition is met, stopping training iteration, and storing model parameters to complete construction of the neural network model. According to the method, the historical time sequence data and the business data of the customer are converted into the customer data two-dimensional matrix, the relation between the time sequence related data and the customer l